[SX/EIT-MM] Senior AI/Agent Engineer

The role

We are building the next generation of production AI agent systems — systems that reason, plan, call tools, delegate across specialized sub-agents, and deliver real business outcomes end to end. We are looking for a senior engineer who has gone deep on modern machine learning, transformers and agents, and who wants to build at the frontier of what language models and multimodal systems can actually do in production today.

This is not a "wrap an API around an LLM" role. We expect candidates who understand why things work — the mechanics of attention, the failure modes of autoregressive decoding, the cost/latency trade-offs of caching and tool routing, the pitfalls of context engineering at scale. And who can turn that understanding into systems that ship, hold up under load, and keep improving.

What you'll do

• Architect agentic systems — plan, memory, tool use, multi-agent delegation, evaluation loops, guardrails. Pick the right abstraction for the problem, not the one on the hype curve.
• Push model capability into production. Design prompt and context strategies, tool interfaces, retrieval and reranking, structured output, streaming, and evaluation — across text and multimodal inputs (vision, documents, audio).
• Own the evaluation story. Build offline eval sets, online LLM-as-judge loops, regression harnesses. Know the difference between a metric that moves your users and a metric that moves only your dashboard.
• Squeeze the system. Prompt caching, batching, speculative decoding, model routing, token budget management, latency targets. Know your P50/P99 and why they look the way they do.
• Contribute upstream. Read SDK source when docs are thin, open PRs against open-source agent frameworks, write crisp bug reports when a vendor's orchestration service returns a weird 500.
• Mentor and set the bar. Your design reviews, code reviews and technical writing shape how the rest of the team thinks about agents.

This is a senior role. We expect candidates who:

• Can scope an ambiguous agent problem, pick an architecture, ship a v1, and know what to measure to decide whether v2 is worth building.
• Have built agent systems that handle real users, real data, real money — not just demos.
• Stay current — reading papers, trying new models the week they drop, benchmarking their own stacks.
• Raise the quality of the team around them.

Required experience

• Solid ML fundamentals. You can explain transformers — attention, positional encoding, KV cache, tokenisation, sampling — without hand-waving. You've read at least a few core papers in full, not just the abstracts.
• Deep LLM application experience. Multiple production systems built on top of frontier models (Anthropic, OpenAI, Gemini, open-weight). You know the practical edge cases: tool-use stability, structured-output failure modes, long-context degradation, prompt-injection defence, cost control.
• Agent systems depth. You've built something with real agent behaviour — planning, memory, tool orchestration, multi-step execution, error recovery — not a single prompt in a loop. Experience with multi-agent coordination (delegation, sub-agent protocols, MCP-style tool servers) is a strong plus.
• Multimodal experience. Hands-on work with vision-language models, document AI (OCR, layout, tables), or audio — end-to-end from ingest to grounded output.
• Strong engineering craft. Python at a senior level — async, typing, testing, packaging, observability. Able to read and navigate a large codebase. Git hygiene that makes reviewers' lives easier.
• Production mindset. Metrics, alerts, eval gates, safe rollouts. You think about what happens at 3am when the model provider degrades, not just about the happy path.
• Fluent with modern coding agents. You use Claude Code / Cursor / Copilot / equivalents daily as a force multiplier. You understand where they shine and where they fail, and you can design prompts, context and tool boundaries to get the most out of them.
• Communication. Writes and speaks clearly in English. Additional language(s) are a plus.

Strongly preferred

• Published ML work (papers, workshop submissions, open-source projects, technical deep-dive blog posts) that shows original thinking.
• Experience fine-tuning, distilling, or post-training open-weight LLMs — SFT, DPO, RLHF, LoRA — even at small scale.
• Experience with vector search, retrieval-augmented generation, reranking at scale.
• Experience shipping production evaluation infrastructure (eval sets, online judges, A/B for LLM systems).

Cloud-native production experience — containerised services, CI/CD, observability (Open Telemetry, traces, metrics, logs).

This position will be contracted through Bosch’s external vendor under a 1-year contract. Salary and benefits will be discussed during interview