Krakow, Lesser Poland Voivodeship, Poland · Hybrid
About the Role: We're looking for a senior AI engineer who thinks in context strategies, agent architectures, and quality feedback loops-and can also write solid backend code. This is a production AI engineering role, no…
Skills: Python, LLM Orchestration, Prompt Engineering, Agentic Workflows, Backend Development
Sign up with Clera and we'll reach out the moment a role actually fits you — no more spraying applications into the void.
Design and evolve AI context architectures and agentic workflows to solve real customer problems. Own the end-to-end production lifecycle, including backend Python development, observability, and quality evaluation.
Requires 3+ years of experience shipping production AI/LLM features and proficiency in production-grade Python. Must have hands-on experience with agentic systems, context design, and the daily use of AI development tools.
About the Role:
We're looking for a senior AI engineer who thinks in context strategies, agent architectures,
and quality feedback loops-and can also write solid backend code. This is a production AI
engineering role, not research or data science. You'll own significant parts of our AI engine, ship
agentic workflows end-to-end, and drive measurable quality improvements on real customer
problems.
You'll be autonomous, hold systems end-to-end, and use AI tools as a natural part of your
daily workflow. You'll raise the engineering bar across the team through clean code, systematic
testing, and sharp code reviews.
Responsibilities:
• Own the AI engine: Design and evolve context architectures (templates, few-shot examples,
structured outputs); manage context window limits; optimize for quality and cost; validate
schemas and handle edge cases
• Architect and ship agentic workflows: Design agent boundaries, clean tool interfaces, failure
handling, and human oversight points; manage agent state across turns; ensure robustness
through guardrails and graceful degradation
• Drive AI quality: Define success criteria before shipping; build and run eval sets; catch
regressions before users do; analyze failure patterns systematically; iterate on evidence, not
gut feel
• Own AI production operations: Trace LLM calls and agent steps across the stack; monitor
cost and latency; set SLOs; respond to incidents; establish operational runbooks
• Write solid Python backend code: Build APIs, microservices, and database schemas that
support the above; own deployment and on-call for your services
• Raise the engineering bar: Champion clean code, the testing pyramid, and sharp code reviews
across the team
Must-Have Requirements:
• 3+ years shipping AI/LLM-powered features in production (not research, not prototypes)
• Hands-on context architecture design: Prompt engineering, structured outputs, schema
validation, few-shot design, context window optimization
• Experience building and operating agentic systems: Tool interface design, orchestration
patterns, failure handling, agent state management, multi-turn conversations
What You'll Work On in Your First 3 Months:
• Build and ship a new agentic workflow end-to-end — design, tools, evals, rollout to a real client
• Tackle a class of LLM reliability issues (e.g. streaming timeouts with reasoning models,
gateway fallback edge cases)
• Close observability gaps so a single conversation can be traced cleanly across our stack
Nice to Have:
• Experience with LLM orchestration frameworks (LangChain, LlamaIndex, LangGraph, etc.)
• Multi-agent system design and operation
• Model routing, cost governance, or LLMOps tooling
• Familiarity with evaluation frameworks (LangSmith, RAGAS, custom harnesses)
• Observability tooling (Datadog, Grafana, OpenTelemetry, Langfuse)
• AWS infrastructure experience (Terraform, Ansible)
• Node.js or TypeScript backend experience
Why Join Us:
Interested in joining our team? Send your CV and a brief cover letter.
Please include:
• Your GitHub profile or portfolio (if available)
• A brief note on your experience with AI/LLM tools
• Your availability and preferred start date
We review applications on a rolling basis and aim to respond within 5 business days.
AI That Prevents Injuries and Losses Before They Happen
Soter helps insurers and industrial leaders prevent workplace risk before it happens. Our AI-driven platform automates safety workflows, analyzes incident data, and turns risk intelligence into measurable results.
Offices: 515 N State St, Chicago, Illinois 60654, US · London, UK W149PB, GB · Perth, Western Australia 6000, AU · Paris, FR
AI That Prevents Injuries and Losses Before They Happen
Soter helps insurers and industrial leaders prevent workplace risk before it happens. Our AI-driven platform automates safety workflows, analyzes incident data, and turns risk intelligence into measurable results.
Offices: 515 N State St, Chicago, Illinois 60654, US · London, UK W149PB, GB · Perth, Western Australia 6000, AU · Paris, FR
