As a Senior AI Engineer, you'll own the design and reliability of the LLM agents at the heart of our AI-powered platform. This is a hands-on individual-contributor role for someone ready to build agents that run in production, and keep them fast, correct, and observable at scale.
Your work will include:
- Designing, building, and hardening LLM agents with real tool use and multi-step orchestration for data quality, catalog, and governance tasks.
- Owning agent reliability end to end — latency, correctness, and cost — including evaluation harnesses and production observability.
- Designing and evolving our agent tooling layer, including MCP servers and protocol-level integrations, so capabilities can be exposed cleanly and securely.
- Building and tuning RAG pipelines and grounding strategies where agents need reliable access to customer data and metadata.
- Working across our LLM gateway (LiteLLM proxy) and model providers to route, monitor, and optimize inference.
- Setting technical standards for how we build agents, and raising the bar for the whole team through design reviews and pragmatic architectural trade-offs.
What we're looking for
- Strong, modern Python, and the engineering judgment of someone who has been senior for a while — you can be trusted with an ambiguous problem and a production system.
- A track record of delivering a product or service end to end: you scoped it, built it, shipped it to real users, and kept it running. Not just features inside someone else's architecture.
- A you-build-it-you-run-it mindset by conviction, not obligation — you've been on call for your own code, you've written the runbook, you've done the postmortem.
- Solid grasp of production fundamentals: observability, testing strategy, CI/CD, incident response, and the operational cost of design decisions.
- Comfort designing and operating services in cloud and Kubernetes environments.
- Experience working with LLM APIs in production code (any provider) — you don't need to have built agents, but you should have shipped something backed by a model and dealt with what goes wrong.
- Genuine engagement with where AI engineering is going — you follow how the field is moving and can reason about what's real versus noise. You've either built agents already, or you're set on mastering it here: this team's work is agentic, and we expect you to get there fast.
- Healthy skepticism toward hype — you surface trade-offs before recommending a direction, and you say so when the simpler option is the right one.
- Candid, low-ego collaboration with product, design, and other engineers.
Nice to have
- Experience building LLM agents that ran in production — tool calling, multi-step orchestration, and the failure modes that come with them.
- Practical experience with MCP (or comparable protocol/tooling design), and the judgment to know when a protocol layer is worth it.
- RAG, retrieval, and grounding techniques, and a realistic view of their limitations.
- LLM gateways and proxies (e.g. LiteLLM) and provider APIs (Azure AI Foundry, OpenAI, or similar).
- Agent-specific evaluation and quality measurement.
- Background in data management, data quality, or governance.
- OAuth2/SSO and multi-tenant service design.
Ataccama is proud to be an Equal Opportunity Employer. We know diversity fuels knowledge exchange, fosters innovation, and empowers us to grow and be better as a company and as humans.
We offer equal opportunities
Ataccama is proud to be an Equal Opportunity Employer. We know diversity fuels knowledge exchange, fosters innovation, and empowers us to grow and be better as a company and as humans. We seek to recruit, develop, and retain the most talented people from a diverse candidate pool.
We are committed to fair and accessible employment practices. If you are contacted for a job opportunity, please let us know how we can best meet your needs and advise us of any accommodations required to ensure fair and equitable access throughout the recruitment and selection process. Accommodation requests can be sent to jobs@ataccama.com.