Solution Engineer (GenAI Specialist)

Experience: 3-5yrs

Location: Ahmedabad, Gujarat (On-site)

URL: www.teaminnovatics.com

Key Responsibilities:

• GenAI & LLM Development:

  Design and build production-grade

  Retrieval-Augmented Generation (RAG)

  pipelines and agentic workflows using frameworks like LangChain or LlamaIndex.

• System Architecture:

  Independently develop scalable backend modules for AI solutions, including chatbots, semantic search engines, and multi-modal analysis tools (Text + Vision).

• Prompt Engineering & Optimization:

  Implement advanced prompt strategies (Chain-of-Thought, ReAct) and optimize LLM performance (latency, token usage, cost) for client deliverables.

• Evaluation & Quality Assurance:

  Set up automated evaluation pipelines (using frameworks like RAGAS or TruLens) to measure hallucination, faithfulness, and answer relevance.

• Integration:

  collaborate with project leads to integrate GenAI modules with existing enterprise data (SQL/NoSQL) and external APIs.

• Pre-Sales & PoC:

  Rapidly prototype Proof of Concepts (PoCs) to demonstrate GenAI capabilities to clients and support technical pre-sales discussions.

Required Skills (Must Have)

• Core Programming:

  Strong proficiency in

  Python

  for backend development and ML pipelines.

• GenAI Frameworks:

  Hands-on experience with

  LangChain

  ,

  LlamaIndex

  , or

  Haystack

  for building complex LLM applications.

• Vector Databases:

  Proficiency with vector stores such as

  Pinecone

  ,

  Weaviate

  ,

  Milvus

  , or

  pgvector

  for managing embeddings.

• LLM APIs:

  Deep familiarity with integrating and fine-tuning models via APIs (OpenAI GPT-4, Azure OpenAI, Anthropic Claude, Gemini).

• API Development:

  Advanced experience with

  FastAPI

  or

  Flask

  for serving AI models as RESTful endpoints.

• Computer Vision:

  Practical experience with

  OpenCV

  or

  multimodal LLMs

  (e.g., GPT-4V, LLaVA) for image-to-text workflows.

Technical Skills

• GenAI Techniques:

• RAG Architecture:

  Chunking strategies, hybrid search (keyword + semantic), and re-ranking algorithms.

• Prompt Engineering:

  Few-shot prompting, prompt templates, and output parsing.

• Fine-tuning (Bonus):

  Exposure to PEFT/LoRA for efficient fine-tuning of open-source models (Llama 3, Mistral).

• MLOps & Deployment:

• Containerization:

  Docker/Kubernetes for deploying LLM services.

• CI/CD:

  Version control for code and prompts; automated testing for AI capabilities.

• Data Engineering:

• SQL & NoSQL:

  Ability to design schemas for storing chat history, user feedback, and metadata (PostgreSQL, MongoDB, DynamoDB).

Business Understanding

• Problem Translation:

  Translate vague business requirements into specific technical GenAI architectures (e.g., "Reduce support tickets" $\rightarrow$ "Build a RAG-based Q&A bot with confluence integration").

• Cost Management:

  Estimate and monitor token consumption and cloud infrastructure costs for proposed solutions.

• Risk & Compliance:

  Awareness of data privacy (PII masking), security, and ethical guardrails in AI generation.

Soft Skills & Professional Habits

• Rapid Prototyping:

  Ability to "fail fast" and iterate quickly on small PoCs to prove value to clients.

• Continuous Learning:

  Proactive in tracking the fast-moving GenAI landscape (new models, papers, tools).

• Collaboration:

  Effective cross-functional communication with data engineers (for pipelines) and business analysts.

Recommended Certifications (Optional but Preferred)

• Generative AI:

  DeepLearning.AI Generative AI with LLMs, or similar vendor-specific certs (AWS/Azure).

• Cloud:

  Azure AI Engineer Associate / AWS Certified Machine Learning Specialty.