Senior Generative AI Architect

Coforge; United States; On-site; USD 180,000 - 230,000; Full time

Job summary

Coforge is seeking a Senior Generative AI Architect to design, build, and scale enterprise AI solutions. You will shape architecture, tuning, evaluation, and deployment strategies across product lines.

Responsibilities include prompt engineering, RAG design, model lifecycle, and system observability. Strong cloud-native, containerization, and orchestration skills are essential for success.

Qualifications

• Hands-on experience with generative AI solutions.

Responsibilities

• Fine-tuning models with defined convergence criteria.
• Rationale for model architecture choices (Transformer vs. classical ML).
• Handling pre-trained vs. custom models.
• Choosing loss functions with business/technical rationale.
• Mitigating gradient issues (vanishing/exploding).
• Addressing data imbalance (resampling, synthetic data).
• Ranking mechanisms and embedding logic.
• Drift detection and remediation strategies.
• Model evaluation, monitoring and retraining pipelines.
• Observability and feedback loops for metrics.
• Deployment validation and A/B testing approaches.
• Agentic AI design and prompting strategies.
• Tool integration and context management patterns.
• RAG design and optimization.

Skills

Fine-Tuning

Model iteration

Transformer architectures

Pre-trained vs custom models

Gradient mitigation

Data handling

Model monitoring

A/B testing

Tools

LangChain

Semantic Kernel

AutoGen

CrewAI

Pinecone

FAISS

Weaviate

Azure AI Search

Docker

Kubernetes

Job description

Job Title/Role: Senior Generative AI Architect

We at Coforge are hiring an experienced Senior Generative AI Architect with strong expertise in Generative AI, cloud-native architecture. The ideal candidate will have a hands-on background in Generative AI solutions, system design, and AI-driven customer experience solutions, with the ability to design, build, and scale intelligent solutions for enterprise clients.

Key Responsibilities:

• Fine-Tuning Experience.
• Iterative training approach: number of cycles, convergence criteria, and evaluation metrics.
• Rationale for selecting model architecture (Transformer vs. classical ML approaches).
• Understanding of pre-trained models vs. custom models.
• Choice of loss functions and their business/technical rationale.
• Gradient-related challenges (vanishing/exploding gradients) and mitigation techniques.
• Handling imbalanced datasets (resampling, weighting, synthetic data generation).
• Ranking mechanisms (e.g., low-rank adaptations, embedding ranking logic).
• Managing model drift (data drift, concept drift detection and remediation strategies).
• Model evaluation, monitoring, and retraining pipelines.
• Observability and feedback loops (model metrics, user feedback integration).
• Deployment validation and A/B testing approaches.

Agentic AI & LLM Application Design:

• Zero-shot vs. few-shot prompting strategies and when to use each.
• Prompt engineering and prompt fine-tuning techniques.

Frameworks & Libraries.

• Experience with agentic AI frameworks (e.g., LangChain, Semantic Kernel, AutoGen, CrewAI).
• Integration patterns for tool usage and orchestration.
• Techniques to manage context windows effectively.
• Retrieval-Augmented Generation (RAG) design and optimization.
• Cost optimization strategies (prompt compression, chunking, caching).
• Trade-offs between latency, cost, and accuracy.
• Design of self-healing systems (retry logic, fallback strategies, tool re-planning).
• Memory management (short-term vs. long-term; local vs. global memory).
• Best practices in agent orchestration and modular design.

Codebase & Project Structure.

• Ideal structure for scalable AI/agentic applications.
• Separation of concerns (prompts, tools, memory, orchestration layers).

LLM Observability & Data Architecture:

LLM Observability.

• Instrumentation and logging strategies.

Vector Databases & Retrieval.

• Experience with vector DBs (e.g., Pinecone, FAISS, Weaviate, Azure AI Search).
• Embedding strategies and indexing mechanisms.
• Distance/similarity metrics (cosine similarity, Euclidean, dot product) and use cases.

Combining Vector DBs with:

• Relational DBs (structured data).
• Metadata stores (filtering, search refinement).
• Designing efficient retrieval pipelines.

MCP / Orchestration Layer.

• Understanding and application of MCP concepts in AI systems.
• Managing communication between models, tools, and services.

Deployment Strategies.

• Containerization (Docker/Kubernetes) and cloud deployment (Azure/AWS/GCP).

Scalability & Reliability.

• Load handling, auto-scaling, and failover mechanisms.
• Performance optimization in production environments.

Good to Have:

• Designing test strategies for deterministic and non-deterministic (AI) systems.
• Establishing measurable benchmarks for LLM performance and system reliability.