Senior Software Engineer, Agentic AI
⚲ Warszawa
15 000 - 20 000 USD netto (B2B)
Wymagania
- Python
- Node.js
- TypeScript
- RAG
- LLM
Opis stanowiska
About us
comm1t is a specialist IT recruitment agency delivering top engineers across Poland and Europe 🇪🇺. We combine experienced recruiters with autonomous AI agents and an obsessive focus on quality — sourcing 24/7 across LinkedIn, GitHub, and beyond to reach engineers who aren't actively job hunting but are open to the right move.
We don't flood you with CVs. We get to know each candidate's skills, values, and goals, then send only the best-matched people — and we stay close through onboarding and the first months to make sure the placement lasts.
About the role
You'll design and ship production AI agents that pull together real-time clinical data, surface proactive care recommendations, and act on behalf of clinicians. This is health tech — clinical AI for older adults living with chronic conditions, where reliability isn't a nice-to-have because it feeds directly into patient outcomes.
You'll carry agent architectures all the way from prototype to production, owning the full lifecycle of AI-powered clinical workflows: retrieval, reasoning, tool use, evaluation, and safety guardrails. Clinicians stay in control of every clinical decision — your job is to make the system around them fast, dependable, and trustworthy.
What you'll do
• Build and deploy clinical AI agents that reason over patient context, call tools, and generate care recommendations
• Own the reliability, observability, and cost efficiency of LLM-powered workflows at scale
• Build and tune RAG pipelines over clinical knowledge bases, treatment protocols, and live patient data
• Develop evaluation frameworks — offline benchmarks, safety tests, regression suites, and LLM-as-judge pipelines wired into CI/CD
• Design multi-step agent orchestration: planning, memory, tool use, error recovery, and human-in-the-loop escalation
• Partner with clinical, product, and engineering teams to turn patient care needs into solid AI system design
• Keep pushing the bar on quality, performance, and architecture as the field moves
Must-have
• 5+ years in software engineering, including 2+ years building AI/ML systems in production
• Hands-on with LLM APIs (OpenAI, Anthropic, open-source models) — prompt engineering, tool use / function calling, structured outputs
• Experience building RAG systems: embeddings, vector stores, retrieval optimization, and grounding
• A track record of end-to-end ownership in a high-growth, fast-paced environment
• Bachelor's or Master's in CS/Engineering, or equivalent hands-on experience
Nice to have
• Agent frameworks and orchestration patterns (tool calling, planners, multi-agent coordination)
• Fine-tuning experience (SFT, RLHF, LoRA) on domain-specific tasks
• Healthcare or regulated-industry background (HIPAA, SOC 2, clinical data handling)
comm1t is a specialist IT recruitment agency delivering top engineers across Poland and Europe 🇪🇺. We combine experienced recruiters with autonomous AI agents and an obsessive focus on quality — sourcing 24/7 across LinkedIn, GitHub, and beyond to reach engineers who aren't actively job hunting but are open to the right move.
We don't flood you with CVs. We get to know each candidate's skills, values, and goals, then send only the best-matched people — and we stay close through onboarding and the first months to make sure the placement lasts.
About the role
You'll design and ship production AI agents that pull together real-time clinical data, surface proactive care recommendations, and act on behalf of clinicians. This is health tech — clinical AI for older adults living with chronic conditions, where reliability isn't a nice-to-have because it feeds directly into patient outcomes.
You'll carry agent architectures all the way from prototype to production, owning the full lifecycle of AI-powered clinical workflows: retrieval, reasoning, tool use, evaluation, and safety guardrails. Clinicians stay in control of every clinical decision — your job is to make the system around them fast, dependable, and trustworthy.
What you'll do
• Build and deploy clinical AI agents that reason over patient context, call tools, and generate care recommendations
• Own the reliability, observability, and cost efficiency of LLM-powered workflows at scale
• Build and tune RAG pipelines over clinical knowledge bases, treatment protocols, and live patient data
• Develop evaluation frameworks — offline benchmarks, safety tests, regression suites, and LLM-as-judge pipelines wired into CI/CD
• Design multi-step agent orchestration: planning, memory, tool use, error recovery, and human-in-the-loop escalation
• Partner with clinical, product, and engineering teams to turn patient care needs into solid AI system design
• Keep pushing the bar on quality, performance, and architecture as the field moves
Must-have
• 5+ years in software engineering, including 2+ years building AI/ML systems in production
• Hands-on with LLM APIs (OpenAI, Anthropic, open-source models) — prompt engineering, tool use / function calling, structured outputs
• Experience building RAG systems: embeddings, vector stores, retrieval optimization, and grounding
• A track record of end-to-end ownership in a high-growth, fast-paced environment
• Bachelor's or Master's in CS/Engineering, or equivalent hands-on experience
Nice to have
• Agent frameworks and orchestration patterns (tool calling, planners, multi-agent coordination)
• Fine-tuning experience (SFT, RLHF, LoRA) on domain-specific tasks
• Healthcare or regulated-industry background (HIPAA, SOC 2, clinical data handling)
🔍 Dekoder Ogłoszenia
🔴
obsessive focus on quality
Może oznaczać bardzo wysokie standardy jakości, ale też potencjalnie długie i żmudne procesy weryfikacji.
🟡
sourcing 24/7 across LinkedIn, GitHub, and beyond
Agencja aktywnie poszukuje kandydatów, co może oznaczać dużą liczbę ofert i potencjalnie mniejszą selektywność w początkowej fazie.
🔴
We don't flood you with CVs.
Obietnica selektywnego dopasowania kandydatów, ale faktyczna jakość selekcji zależy od umiejętności agencji.
🟡
stay close through onboarding and the first months to make sure the placement lasts.
Agencja oferuje wsparcie po zatrudnieniu, co jest pozytywne, ale może też sugerować, że problemy z utrzymaniem pracownika są częste.
🟡
carry agent architectures all the way from prototype to production
Oznacza pełną odpowiedzialność za cykl życia produktu, od koncepcji po wdrożenie, co może być zarówno wyzwaniem, jak i szansą na rozwój.