CES has 26+ years of experience in delivering Software Product Development, Quality Engineering, and Digital Transformation Consulting Services to Global SMEs & Large Enterprises. CES has been delivering services to some of the leading Fortune 500 Companies including Automotive, AgTech, Bio Science, EdTech, FinTech, Manufacturing, Online Retailers, and Investment Banks. These are long-term relationships of more than 10 years and are nurtured by not only our commitment to timely delivery of quality services but also due to our investments and innovations in their technology roadmap. As an organization, we are in an exponential growth phase with a consistent focus on continuous improvement, process-oriented culture, and a true partnership mindset with our customers. We are looking for the right qualified and committed individuals to play an exceptional role as well as to support our accelerated growth.
You can learn more about us at: http://www.cesltd.com/
We’re looking for a hands-on AI Engineer to design, build, and ship customer-facing, production-grade features powered by modern LLMs. You’ll partner with product, data, platform, and Customer Experience/Support to turn messy real-world problems into reliable, safe, and measurable AI solutions. You’ll close the loop from voice-of-customer insight → model/design choices → launch → telemetry and iteration, with success measured by outcomes like task completion, CSAT, time-to-resolution, and deflection rate—not just model scores.
You will help develop the next-generation agentic platform that powers customer-facing assistants across the entire journey—from discovery and onboarding to in-product guidance and support. These agents will reason, plan, call internal tools/APIs, retrieve knowledge, and escalate to humans gracefully. You’ll collaborate with CX/Support, Product, and Platform to integrate with CRM and knowledge bases, implement memory and personalization, enforce safety/quality guardrails, and run evaluations and A/B tests. Success is measured in real CX outcomes: shorter time-to-resolution, higher FCR/CSAT, lower effort, and reliable containment.
How You'll Drive Success
• Own end-to-end development of LLM features: problem framing, data prep, prototyping, offline/online evaluation, deployment, and monitoring.
• Build retrieval-augmented generation (RAG) pipelines with vector search (e.g., FAISS, Pinecone, OpenSearch/KNN) and document orchestration.
• Implement prompt strategies, tool use/function calling, and guardrails for safety, bias, and privacy.
• Integrate models in production services (REST/GraphQL/gRPC), including auth, rate limiting, and observability.
• Stand up evals and experiment frameworks (A/B tests, golden sets, regression suites) with clear success metrics.
• Optimize for latency, cost, and quality: prompt compression, caching, model selection, fine-tuning/LoRA, distillation where appropriate.
• Collaborate with DevOps/MLOps/Platform to automate CI/CD, data/version management, and feature flags.
• Embed with CX/Support to mine tickets, chats, and call transcripts; convert VOC into training/eval datasets and backlog priorities.
• Instrument user journeys and define online/offline evals (win rate, hallucination rate, TTR, CSAT/NPS); run A/B tests and ship iterative improvements.
• Build feedback loops (thumbs-up/down, rationale capture, escalation) and human-in-the-loop fallbacks that protect quality.
• Own reliability and UX details that matter for customers: latency budgets, safe fallbacks, clear handoff to human agents, accessibility.
• Partner with Trust/Legal/Security to ensure privacy-by-design and compliant data handling; implement guardrails and red-team mitigations.
Success looks like (first 6 months):
• Document designs and teach best practices to engineering partners.
• Ship 1–2 LLM features to production with SLAs, monitoring, and rollback plans.
• Establish an eval harness (offline + online) and quality gates for prompts/RAG.
• Reduce average latency/cost per request by ≥20% without quality regression.
• Create internal runbooks and dashboards for reproducibility and troubleshooting.
What You Bring to Help Us Grow
• Model customization (fine-tuning/LoRA) and synthetic data generation.
• Streaming and toolcalling/agents, structured outputs (JSON, function schemas).
• Cloud & MLOps: AWS (SageMaker/Bedrock/Lambda), Docker, Terraform, Kubernetes.
• Frontend integration patterns for AI UX (streaming UIs, fallbacks, user feedback loops).
• Domain experience in compliance-heavy environments (e.g., education, finance, healthcare).
What You'll Need to Thrive
• 4–6 years in applied ML/AI or backend engineering with measurable production impact.
• Strong Python and software engineering fundamentals (testing, types, CI/CD).
• Practical LLM experience: OpenAI/Anthropic, or cloud providers (AWS Bedrock, Azure OpenAI, GCP Vertex).
• Experience with at least one deep learning or LLM framework (PyTorch, Transformers, vLLM) and one orchestration library (LangChain, LlamaIndex, Guidance, or custom).
• RAG and data pipelines: chunking/embedding strategies, vector DBs, metadata filtering, and document QA.
• Monitoring/telemetry for AI systems (e.g., MLflow, Weights & Biases, Prometheus, custom eval dashboards).
• Security & privacy awareness (PII handling, redaction, data retention).
Tools you may use:
• Python, PyTorch, Hugging Face, vLLM, LangChain/LlamaIndex, FAISS/Pinecone/OpenSearch, Postgres, Redis, Docker, Terraform, GitHub Actions, MLflow/W&B, AWS (Bedrock, SageMaker, Lambda, S3, CloudWatch).
Why CES :
Flexible working hours to create a work-life balance.
Opportunity to work on advanced tools and technologies.
Global exposure to not only collaborate with the team, but also to connect with the client portfolio and build professional relationships.
Highly encouraged for any innovative ideas & thoughts and we support in executing the same.
Periodical and on-spot rewards and recognitions on your performance.
Provides a better platform for enhancing skills via many different L&D programs.
Enabling and empowering atmosphere to work along.