← Back to jobsJob ID col-cmvv2sdju01wg42b9emd69iaz

ClayPosted 30+ days ago

Software Engineer, Applied AI

Full-time
Hybrid
Mid level
$170K – $300K/yr
Posted 30+ days ago

Clay builds AI agents that research, enrich, and act on behalf of go-to-market teams. The Software Engineer, Applied AI will develop agent products and shared infrastructure, improving task completion, reliability, and trust in production.

Posted
30+ Days Ago
Source
jobs.ashbyhq.com
Sector
Information Technology & AI

Opens the employer's application page in a new tab

Responsibilities

  • Design and iterate on agent behavior across real GTM workflows. For example, sourcing a Total Addressable Market (TAM) list, which in practice means navigating ambiguous Ideal Customer Profile (ICP) definitions, reconciling conflicting signals across data sources, and making judgment calls that experienced analysts spend real time on
  • Map manual, multi-step workflows that GTM teams do today and turn them into agent-driven flows that are as good as, or better than, a human doing it by hand
  • Build and run evals that measure whether an agent actually completed the task correctly - not just whether the output looked plausible - and use them to catch regressions and failure modes
  • Analyze real failures in production and systematically improve robustness
  • Work with product to take agent flows from early prototype through closed beta and into general availability, and help define what "good" looks like for each one
  • Build the core agent harness that other teams build on top of, including memory systems, tool infrastructure, and retrieval architecture
  • Improve agent performance through prompting strategies, tool-use design, and context construction
  • Design guardrails and safety checks so agents behave predictably in production
  • Build a cross-surface evals framework so every team building on the platform can measure quality, regressions, and performance the same way
  • Build feedback loops that turn real usage and production logs into better prompts, tools, and eval coverage over time
  • Support teams building their own forks or variants of the managed agent for their specific use case

Qualifications

  • Experience building or shipping production systems with LLMs or agents. This might look like multi-step agent orchestration, prompting and tool-use design, retrieval, structured extraction, or fine-tuning
  • Strong backend fundamentals in APIs, databases, distributed systems
  • Experience with model or agent evaluation: designing evals, measuring regressions, or turning fuzzy quality questions into measurable signals
  • A systems-and-outcomes mindset. You care about whether the product actually works for users, not just about model metrics in isolation
  • Comfort debugging messy, real-world failures and a bias toward shipping and iterating quickly in a space where best practices are still being figured out

Preferred

  • Experience with agent frameworks, tool-calling systems, or retrieval architectures (vector search, hybrid search, RAG)
  • Experience building or maintaining eval/benchmark infrastructure for LLM-based systems, or running fine-tuning in production
  • Experience with GTM, sales, or marketing workflows (e.g. lead sourcing, enrichment, audience building)
  • Familiarity with Clay's stack: React, TypeScript, Python, AWS (Aurora/Postgres, ECS/Fargate, Lambda, OpenSearch, Clickhouse, Elasticache/Redis), Terraform, Datadog
  • A growth mindset - we're building a team that's curious, open-minded, and happy to invest in each other's learning, not just their own

Required skills

API DesignAgent OrchestrationDistributed SystemsFine-TuningModel and Agent EvaluationPrompting and Tool-Use DesignPythonRetrieval-Augmented Generation (RAG)TypeScriptVector Search

Full job description

Clay builds AI agents that research, enrich, and act on behalf of go-to-market teams. The Software Engineer, Applied AI will develop agent products and shared infrastructure, improving task completion, reliability, and trust in production.

Responsibilities

  • Design and iterate on agent behavior across real GTM workflows. For example, sourcing a Total Addressable Market (TAM) list, which in practice means navigating ambiguous Ideal Customer Profile (ICP) definitions, reconciling conflicting signals across data sources, and making judgment calls that experienced analysts spend real time on
  • Map manual, multi-step workflows that GTM teams do today and turn them into agent-driven flows that are as good as, or better than, a human doing it by hand
  • Build and run evals that measure whether an agent actually completed the task correctly - not just whether the output looked plausible - and use them to catch regressions and failure modes
  • Analyze real failures in production and systematically improve robustness
  • Work with product to take agent flows from early prototype through closed beta and into general availability, and help define what "good" looks like for each one
  • Build the core agent harness that other teams build on top of, including memory systems, tool infrastructure, and retrieval architecture
  • Improve agent performance through prompting strategies, tool-use design, and context construction
  • Design guardrails and safety checks so agents behave predictably in production
  • Build a cross-surface evals framework so every team building on the platform can measure quality, regressions, and performance the same way
  • Build feedback loops that turn real usage and production logs into better prompts, tools, and eval coverage over time
  • Support teams building their own forks or variants of the managed agent for their specific use case

Preferred

  • Experience with agent frameworks, tool-calling systems, or retrieval architectures (vector search, hybrid search, RAG)
  • Experience building or maintaining eval/benchmark infrastructure for LLM-based systems, or running fine-tuning in production
  • Experience with GTM, sales, or marketing workflows (e.g. lead sourcing, enrichment, audience building)
  • Familiarity with Clay's stack: React, TypeScript, Python, AWS (Aurora/Postgres, ECS/Fargate, Lambda, OpenSearch, Clickhouse, Elasticache/Redis), Terraform, Datadog
  • A growth mindset - we're building a team that's curious, open-minded, and happy to invest in each other's learning, not just their own
  • Agent Frameworks
  • Tool-Calling Systems
  • Retrieval Architectures
  • Vector Search
  • Hybrid Search
  • Retrieval-Augmented Generation
  • LLM Evaluation Infrastructure
  • Benchmark Infrastructure
  • Production Fine-Tuning
  • GTM Workflows
  • Sales Workflows
  • Marketing Workflows
  • Lead Sourcing
  • Lead Enrichment
  • Audience Building
  • React
  • TypeScript
  • Python
  • AWS
  • Aurora
  • PostgreSQL
  • ECS
  • Fargate
  • AWS Lambda
  • OpenSearch
  • ClickHouse
  • ElastiCache
  • Redis
  • Terraform
  • Datadog
  • Growth Mindset
  • Curiosity
  • Open-Mindedness
  • Collaborative Learning

Benefits

  • Offers Equity
  • All employees can work with world-class coaches who specialize in creativity, management, and more.
  • Hybrid work arrangement

Company

  • Go-to-market data infrastructure and automated revenue-growth workflows
  • New York, New York, USA
  • https://clay.com/
  • Founded in 2017
  • 501-1000 employees

Qualifications

  • Experience building or shipping production systems with LLMs or agents. This might look like multi-step agent orchestration, prompting and tool-use design, retrieval, structured extraction, or fine-tuning
  • Strong backend fundamentals in APIs, databases, distributed systems
  • Experience with model or agent evaluation: designing evals, measuring regressions, or turning fuzzy quality questions into measurable signals
  • A systems-and-outcomes mindset. You care about whether the product actually works for users, not just about model metrics in isolation
  • Comfort debugging messy, real-world failures and a bias toward shipping and iterating quickly in a space where best practices are still being figured out
  • Experience with agent frameworks, tool-calling systems, or retrieval architectures (vector search, hybrid search, RAG)
  • Experience building or maintaining eval/benchmark infrastructure for LLM-based systems, or running fine-tuning in production
  • Experience with GTM, sales, or marketing workflows (e.g. lead sourcing, enrichment, audience building)
  • Familiarity with Clay's stack: React, TypeScript, Python, AWS (Aurora/Postgres, ECS/Fargate, Lambda, OpenSearch, Clickhouse, Elasticache/Redis), Terraform, Datadog
  • A growth mindset - we're building a team that's curious, open-minded, and happy to invest in each other's learning, not just their own

Required skills

  • API Design, Agent Orchestration, Distributed Systems, Fine-Tuning, Model and Agent Evaluation, Production LLM and Agent Systems, Prompting and Tool-Use Design, Python, Retrieval-Augmented Generation (RAG), TypeScript, Vector Search

Experience

  • Mid level

Job details

Employment type

Full-time

Seniority level

Mid level

Date posted

Aug 14, 2026

Work mode

Hybrid

Job source

jobs.ashbyhq.com

Company

Clay

Information Technology & AI

Go-to-market data infrastructure and automated revenue-growth workflows

See all 6 jobs from Clay →
  • New York, New York, USA
  • Information Technology & AI
  • 501-1000 employees
  • Founded 2017
  • clay.com

Similar jobs

Matched on role, skills and location · live jobs only

See more AI Engineer jobs in New York

WTW

1d ago

New

AI Solutions Engineer

Full-timeHybridNew York, NYCompetitive

WTW is hiring an AI Solutions Engineer for its Willis Neuron Technology team, supporting the Risk & Analytics consulting practices of Willis, a WTW business.

Why similarSame rolePythonNew York

Envision Technology Solutions

1d ago

New

Anthropic Claude AI Engineer/Developer

TemporaryHybridNew York, NYCompetitive

Envision Technology Solutions is seeking an Anthropic Claude AI Engineer/Developer to build applications, tools, and agentic workflows using the Claude ecosystem.

Why similarSame rolePythonNew York

Landscape Forms

1d ago

New

Senior Software Engineer – AI & Business Applications

Full-timeRemoteUnited StatesCompetitive

Landscape Forms is hiring a Senior Software Engineer to develop software and AI-powered solutions that improve how teams work across the company.

Why similarSame rolePythonRemote

Get new AI Engineer jobs in New York by email

Create job alert

Software Engineer, Applied AI

Clay · $170K – $300K/yr

Apply on company site