Senior AI Engineer

About DataSpecta

DataSpecta is a Data & AI consulting and engineering company helping organizations transform data into measurable business value through advanced analytics, modern data platforms and enterprise AI solutions.

We design and deliver solutions across both on-premise and cloud environments, working closely with enterprise customers from discovery through production.

Alongside customer projects, we build our own AI products such as CogniSpecta (enterprise knowledge & cognitive search) and CodeSpecta (AI-powered software engineering).

We're looking for a Senior AI Engineer based in Baku, Azerbaijan , with strong software engineering fundamentals and proven experience delivering LLM applications and AI agents to production.

You will design, build and maintain AI agents, retrieval systems and document generation pipelines for an enterprise AI estate, and own root cause analysis on agent incidents.

Location & Work Model

• Location: Baku, Azerbaijan
• Work model: [Hybrid / On-site]

What You Will Work On

• Tool-calling AI agents and agentic workflows
• End-to-end RAG pipelines with citations
• MCP servers and an internal AI Marketplace
• On-premise and self-hosted LLM architectures

Responsibilities

• Build tool-calling agents and multi-step workflows with human-in-the-loop checkpoints
• Implement end-to-end retrieval pipelines, from parsing to reranking and citation
• Integrate agents with SAP, SuccessFactors, email and internal APIs
• Expose agent capabilities as MCP servers
• Build template-based Word, Excel and PowerPoint generation
• Own prompt versioning, production promotion and runbooks
• Instrument agents with tracing and diagnose production failures

Required Qualifications

• Based in Baku or willing to relocate
• 5+ years in software engineering, 2+ delivering LLM or agent systems to production
• Expert Python; production experience with an agent orchestration framework
• Production RAG experience with measured retrieval quality
• Experience with LLM gateways or self-hosted models
• Fluent English

Technical Skills

• Core: Python, asyncio, FastAPI, Pydantic, pytest
• Agent frameworks: LangGraph, LlamaIndex, Semantic Kernel or equivalent
• Protocols: MCP, A2A, OpenAI-compatible APIs
• Retrieval: Hybrid search, reranking, pgvector, Qdrant, OpenSearch
• Document handling: PDF/DOCX/XLSX parsing, OCR, python-docx, openpyxl, python-pptx, Jinja2
• Model serving: vLLM, TGI, Ollama, open-weight models
• Integration: REST, OData, SAP, SuccessFactors, OAuth2/OIDC, Microsoft Graph
• Delivery: Git, Docker, Helm, CI, OpenTelemetry, Langfuse, Arize Phoenix
• Security: OWASP Top 10 for LLMs, prompt injection mitigation

Preferred Qualifications (a plus)

• Regulated financial sector or on-premise/air-gapped delivery experience
• Hands-on SAP or SuccessFactors integration
• Open-source contributions in the agent ecosystem

What We Value

• Curiosity about solving business problems with AI
• Comfort across business, data and technology
• End-to-end ownership
• Continuous learning

Follow us:

• LinkedIn: https://www.linkedin.com/company/innovance-consultancy
• LinkedIn: https://www.linkedin.com/company/dataspecta
• Instagram: https://www.instagram.com/innovanceconsultancy
• Instagram: https://www.instagram.com/dataspecta