Senior AI Engineer, Agents
New
E
EveryWatchWatch Market Data
Greece. Spain. Portugal. Ukraine. IndiaFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 6+ years shipping production software, of which 2+ on LLM systems
- Required Skills
- AWSDockerPythonFastAPICI/CDLLM
Requirements
- 6+ years shipping production software.
- 2+ years experience building LLM systems for real users.
- Deep expertise in agentic patterns: ReAct loops, tool calling, planning, state management, and memory.
- Hands-on experience with LangGraph and observability stacks like LangSmith or Langfuse.
- Production-grade Python development using FastAPI and asynchronous processing.
- Advanced RAG implementation including re-ranking, relevance judgment, and evaluation.
- Experience with cloud production environments (AWS Bedrock, SQS, EC2/EKS, S3).
- Proficiency with Docker and CI/CD pipelines.
- Ability to implement evaluation as a core habit (RAGAS, DeepEval, LLM-as-judge).
- Strong architectural mindset for long-term platform stability and scalability.
Responsibilities
- Invent the agent roadmap by collaborating with sales, data, and product teams to identify and prioritize high-impact automation use cases.
- Design and build agent architecture, including tools, loops, sub-agents, memory, state, and evaluation frameworks.
- Develop and maintain a platform for scalable agent creation, including shared tool layers and MCP integrations.
- Harden WatchChat by optimizing for multi-turn state, latency, cost, reliability, and regression testing.
- Implement rigorous quality measurements using golden datasets, programmatic verifiers, and LLM-as-judge frameworks.
View Full Description & ApplyYou'll be redirected to the employer's site
