AI Engineer / Senior AI Engineer

Elios, Inc.; Berlin; Remote; EUR 86,000 - 98,000; Full time

Job summary

Elios, Inc. is seeking an AI Engineer to lead the design and build of production agents and LLM features for a specialized financial advisory firm. You will own the work end to end, from architecture through production hardening, ensuring robust streams, deduplicated tool calls, and validated structured output.

The role is fully remote for UK or Germany-based engineers on a 6 to 8 month contract. You will work across agent-runtime, LLM integration, evaluation frameworks, and telemetry, mentoring

Qualifications

• Mid-level to senior experience building production LLM/agent systems.
• Experience with tool/function calling, structured output, and streaming.
• Strong Python or equivalent backend language and testing discipline.
• Experience building evaluation pipelines or quality gates for models and prompts.
• Mentoring and raising team standards.

Responsibilities

• Lead the design and development of agents and LLM features end to end, from architecture through production hardening.
• Architect core agent-runtime capabilities: session lifecycle, SSE streaming with reconnect and de-duplication, crash-safe tool dispatch, and structured outputs.
• Build provider-agnostic LLM client with JSON-schema output, streaming tool use, and a templating/versioning system.
• Own evaluation frameworks and quality gates for shipping model and prompt changes.
• Tackle reliability challenges like streaming reliability, tool-call correctness, and cost versus latency.
• Implement telemetry for token usage, latency, cost, and outcome quality.
• Design integration layer with mock seams and columnar analytics for agents reasoning over data.
• Mentor engineers and establish patterns for the team.

Skills

LLM/Agent systems

Python backend

Testing discipline

Mentoring

Remote work readiness

Tools

Anthropic API

DuckDB

LLM client libraries

Job description

Location: Remote (UK or Berlin, Germany) | Type: Contract (6 to 8 months) | Experience: Mid-level to Senior | Pay: $70-$80/hr USD

About the Role

We're hiring an AI Engineer to lead the design and build of production agents and LLM features for a specialized financial advisory firm. You'll own the work end to end, from architecture through the unglamorous production hardening that decides whether an agent actually holds up: streams that reconnect cleanly, tool calls that never fire twice, structured output that validates every time.

The firm is backed by global private equity, serves the Office of the CFO, and is building an AI-native managed services platform for finance and accounting work. This role sits at the center of the agent runtime and the LLM layer that everything else on the platform depends on.

It's a fully remote, 6 to 8 month contract open to engineers based in the UK or Germany. If you'd rather solve the hard reliability problems in agent systems than build another demo, this is the role.

What You'll Do

• Lead the design and development of agents and LLM features end to end, from architecture through production hardening
• Architect core agent-runtime capabilities: session lifecycle, SSE streaming with reconnect and de-duplication, crash-safe tool dispatch, and structured and streaming model integration
• Build out the provider-agnostic LLM client (text, JSON-schema structured output, streaming tool use) and the prompt registry behind it, with templating and versioning
• Own the evaluation frameworks and quality gates the team relies on to ship model and prompt changes with confidence
• Take on the ambiguous, high-impact problems, like streaming reliability, tool-call correctness, and cost versus latency trade-offs
• Telemetry over LLM requests and background jobs, so token usage, latency, cost, and outcome quality are always visible
• Compose tools and actions across both self-hosted and cloud-sandbox execution models
• Work on the integration layer and its mock seams, plus columnar analytics where agents reason over data
• Mentor engineers on craft, conventions, and judgment. A big part of this role is setting the patterns others follow.

Qualifications

• Mid-level or senior experience building production LLM or agent systems, including tool/function calling, structured output, prompts, and streaming, and a working knowledge of how each one fails
• Strong systems engineering in Python (or a comparable backend language) with sound architectural judgment
• Rigorous testing discipline: dependency injection, boundary mocks, and tests that assert behavior rather than implementation
• Experience building evaluation pipelines or quality gates for model and prompt changes
• A mentoring instinct and a track record of raising the quality of the engineers around you
• Based in the UK or Germany and comfortable working fully remote

Nice to Have

• Hands-on Anthropic API experience: Claude tool use, the Managed Agents API, MCP, or Skills
• Familiarity with actor or agent frameworks and columnar analytics tools like DuckDB
• Background in finance, accounting, audit, or another regulated domain

Why Join Us

You'll join a small, senior engineering group inside a firm with deep finance and accounting expertise that's now turning that expertise into software. The bar is production quality, not prototypes, and the problems are the ones most teams skip: correctness, reliability, and cost at scale.

If you want your judgment to shape how an agent platform gets built, and to see that work run against real financial workflows, this one is worth a conversation.