Job Description
About TYN:
TYN (The Yellow Network) is an innovation consulting & AI solutions company helping enterprises accelerate digital transformation through AI, GenAI agents, ML systems, and co-innovation programs. We work with mid-large enterprises across Manufacturing, Automobile/3PL, Retail, and BFSI, designing and delivering high-impact AI solutions and operational AI systems. TYN also builds NiFo 2.0, an AI accelerator & agentic capability toolkit, used to drive structured innovation workflows, solution discovery, AI CoE readiness and Governance for our customers.
Key responsibilities:
1. AI Solution Design
·
End-to-end AI systems including GenAI agents, RAG platforms, document intelligence, AI copilots, knowledge automation, and predictive ML models.
·
Design multi-agent architectures (task planning, tool-use orchestration, bounded autonomy, safety mechanisms).
·
Define data pipelines, feature stores, embedding pipelines, and vector DB schemas (pgvector/Qdrant/Pinecone).
·
Select appropriate LLMs (OpenAI, Azure, Claude, Llama 3, proprietary) based on cost, latency, and compliance.
·
Own MLOps & LLMOps patterns (prompt management, versioning, evaluation, safety, telemetry).
2. Technical Leadership for Customer Projects
·
Lead AI discovery, architecture workshops, and solution storyboarding with client CTO/CIO/Innovation teams.
·
Translate business problems into architecturally sound AI solutions.
·
Supervise development teams (internal developers + interns) through design, build, test, and rollout. Review and approve all technical designs, APIs, pipelines, and prompt architectures.
3. Engineering Excellence & Governance
·
Establish coding standards, LLMOps patterns, CI/CD for AI systems.
·
Ensure systems meet security best practices (data redaction, encryption, policy enforcement).
·
Implement performance tuning, caching, batching, cost optimization, and telemetry for LLM-heavy workloads.
·
Mentor junior engineers and interns through hands-on guidance.
Qualifications:
Bachelor's or Master's degree in Computer Science, Engineering, MCA or a related field.
4+ years in software engineering / architecture with 2+ years in AI/ML or GenAI systems.
Strong experience in Python (FastAPI/Django), LangChain/LlamaIndex, vector DBs, and cloud AI services.
Expertise in Azure AI Studio or Google Cloud / Vertex AI or AWS Bedrock, embeddings, token optimization, and production GenAI deployments.
Strong grounding in ML fundamentals (classification, NLP, embeddings, transformers).
Experience designing scalable backend architectures (microservices, event-driven systems).
Strong understanding of security, RBAC, multi-tenancy, and data governance.
Location: Chennai or Coimbatore
