Senior LLM / Generative AI / Agentic Solutions Engineer
Role Overview
We are seeking a Senior LLM / Generative AI / Agentic Solutions Engineer to design, build, and deploy agentic AI systems that operate reliably in production environments. In this role, you will own the full lifecycle of Generative AI capabilities—from model adaptation and retrieval to orchestration, evaluation, and operational excellence.
You will work on complex, real-world systems where agents must plan, call tools, manage context, and execute safely and efficiently within enterprise workflows.
Key Responsibilities
Agentic AI Systems
- Design and implement agent-based architectures, including supervisor, planner, and executor patterns
- Develop routing, memory, and context-management strategies
- Implement robust tool/function calling and failure-handling mechanisms
LLM Adaptation & Deployment
- Fine-tune or parameter-efficiently adapt open-source LLMs (e.g., LoRA, QLoRA, PEFT)
- Optimize inference for latency, throughput, and cost
- Deploy models safely into production environments
Retrieval-Augmented Generation (RAG)
- Build high-quality RAG pipelines including:
- Embeddings
- Retrieval and re-ranking
- Grounding and citation strategies
- Optimize for accuracy, speed, robustness, and cost efficiency
Reliability & Structured Generation
- Enforce structured outputs using schemas and validations
- Implement guardrails, post-processing, and hallucination mitigation strategies
- Improve system robustness and predictability
Evaluation & Quality Assurance
- Create automated evaluation frameworks for LLMs and agents
- Implement offline benchmarks and online monitoring
- Maintain regression tests, prompt versioning, and model version control
Production Engineering
- Build and operate containerized services and APIs
- Implement CI/CD pipelines, observability, and reliability best practices
- Define and monitor SLOs, alerts, and incident readiness
Collaboration & Leadership
- Work cross-functionally with product, platform, and data teams
- Integrate GenAI capabilities into user-facing and internal workflows
- Mentor engineers and promote best practices in applied GenAI engineering
Must-Have Qualifications
- 5+ years of experience building production ML/AI systems
- 2+ years operating at senior or lead level
- Strong Python engineering skills (testing, packaging, performance profiling)
- Hands-on experience deploying LLMs and agentic AI systems in real-world applications
- Proven experience with LLM adaptation and quality/safety evaluation
- Production experience implementing RAG systems
- Solid MLOps fundamentals: containers, CI/CD, monitoring, versioning
- Backend/API development experience (REST or gRPC), including authentication and resilience patterns
- Comfortable working in cloud environments (AWS, GCP, or Azure) under production constraints
Preferred / Nice-to-Have
- Inference optimization experience (quantization, caching, batching, GPU serving such as vLLM or TGI)
- Agent safety engineering (prompt injection defense, tool security, sandboxing, red teaming)
- Advanced evaluation techniques (LLM-as-judge, preference testing, rubric-based scoring, A/B testing)
- Experience operating and tuning vector databases
- Workflow or event-driven orchestration tools (e.g., Temporal, Airflow, n8n, or similar)
- Multi-lingual GenAI systems and internationalization best practices
If you want, I can:
- Adapt this to a LinkedIn or startup-style JD
- Rewrite it with a stronger commercial / AI-lab tone
- Convert it into a headhunter pitch
- Align it to EU / US / global seniority expectations
Just tell me how you’ll be using it.
