It's fun to work in a company where people truly BELIEVE in what they are doing!
We're committed to bringing passion and customer focus to the business.
Job Description: Gen AI Engineer
Responsibilities:
Design, develop, and implement advanced solutions leveraging Large Language Models (LLMs).
Take full ownership of initiatives, delivering end-to-end solutions with minimal supervision.
Stay current with the latest advancements in Generative AI, LLMs, RAG systems, and applied research.
Build and maintain reusable code libraries, tools, and frameworks to accelerate AI development.
Participate in code reviews to ensure high-quality, maintainable, and scalable solutions.
Contribute across the entire software development lifecycle—design, implementation, testing, deployment, and maintenance.
Collaborate with cross-functional teams to align AI solutions with business goals, integrate contributions into core systems, and influence roadmaps.
Apply strong analytical and problem-solving skills to design efficient solutions for complex business challenges.
Communicate effectively across technical and non-technical teams, ensuring transparency and alignment.
Own business impact of AI solutions, including adoption, accuracy, latency, and cost efficiency
Translate ambiguous business problems into structured AI solution approaches and measurable outcomes
Drive solution success metrics (e.g., productivity gains, automation %, decision accuracy)
Engage directly with business and technical stakeholders to understand requirements, present solutions, and influence decision-making
Communicate solution architecture and trade-offs clearly to both technical and non-technical audiences
Contribute to client discussions, PoCs, and proposal development.
Design scalable, modular, and production-grade AI systems (APIs, pipelines, orchestration layers)
Define architecture patterns for LLM applications (RAG pipelines, agentic workflows, hybrid systems)
Make trade-offs across latency, cost, accuracy, and maintainability
Build reusable accelerators, frameworks, and components that can be leveraged across multiple use cases and clients
Contribute to internal IP creation (assets, templates, reference architectures)
Ensure reliability and robustness of LLM systems through evaluation frameworks, guardrails, and fallback strategies
Design safe and responsible AI systems (hallucination mitigation, bias handling, governance)
Optimize cost-performance trade-offs in large-scale deployments
Identify when NOT to use LLMs and propose alternative approaches
Contribute to code reviews, design reviews, and mentorship of junior team members
Drive quality standards and best practices across projects
Stay ahead of advancements in GenAI and proactively evaluate their applicability to business problems
Contribute to internal knowledge sharing, training, and capability building.
Must-Have Skills:
Generative AI & NLP:
SaaS-based LLMs: LangChain, LlamaIndex, vector databases, prompt engineering (CoT, ReAct, agents), Azure OpenAI function calling, multimodal models.
Open-Source and SaaS LLMs: Azure OpenAI, Claude Opus 4.6, GPT-3.5 Turbo, GPT-4, etc.
At least one agentic Generative AI framework: CrewAI, AutoGen, LangGraph, n8n, LangFlow, SmolAgents, Semantic Kernel.
Advanced Retrieval-Augmented Generation (RAG) systems: hybrid retrieval, knowledge graph–based retrieval, multi-hop RAG, hierarchical/contextual retrieval strategies, evaluation/monitoring of RAG pipelines.
Classical NLP: text classification, topic modeling, Q&A systems, conversational AI/chatbots, search, Document AI, summarization, content generation, and Named Entity Recognition (NER).
Databricks ecosystem: Databricks Genie, Databricks AI/BI, AgentBricks
MS Copilot Studio and knowledge on no-code/low-code app development.
MCP server, tools, skills and creation and maintenance of reusable components.
Tech Stack:
Programming & Frameworks: Python, FastAPI
Cloud & DevOps: Azure DevOps, Agile (Azure Boards)
AI/ML Tools:…