We are seeking an AIML engineer ready to work with a Huge IT Company at Navi Mumbai loc. Ready to work full time 5 days from office.

Please share your updated resume on [email protected].

Or else whatsapp me at (phone hidden).

Role & responsibilities

Exp - 4+ yrs

Location - Navi Mumbai

Mode - Work from Office

Immediate Joiners or ready to join within 20-30 days max

Build, implement, and operate Generative AI, machine learning, and inference services that run reliably on enterprise onprem infrastructure, with a strong focus on security, scalability, and observability.

Key Responsibilities are as follows :

- Build endtoend ML and GenAI solutions: data ingestion, model training, finetuning, serving, and monitoring.
- Containerize models and pipelines using best practices for Kubernetes and OpenShift Operators; create reproducible CI/CD for model lifecycle.
- Implement secure deployments: secrets management, RBAC, network policies, image signing, and runtime hardening for onprem clusters.
- Optimize inference for latency, throughput, and resource efficiency on GPU/CPU nodes; implement autoscaling and batching strategies.
- Operationalize MLOps: model versioning, drift detection, explainability, logging, and SLA enforcement.
- Build observability and governance: metrics, tracing, logging, drift detection, explainability, lineage, and audit trails.




- Integrate Vector Databases into retrieval and RAG pipelines: Build embedding pipelines, manage vector DB deployments, tune similarity search, and ensure secure access and scaling.
- Collaborate crossfunctionally with SRE, security, and compliance teams to meet enterprise governance and audit requirements.

Preferred candidate profile

- Robust proficiency in Python, ML frameworks (PyTorch, TensorFlow), and model serving tools (TorchServe, Triton, KFServing).
- Deep experience with Kubernetes and Red Hat OpenShift deployment patterns, Operators, and security features.
- Proven track record of deploying onprem AI workloads with GPU orchestration, resource tuning, and persistent storage.
- Solid understanding of security controls for ML: encryption at rest/in transit, secrets, identity, and access management.
- Experience with CI/CD for ML (Git, MLFlow, etc.), infra as code (Ansible, Terraform), and observability stacks (Prometheus, Grafana, ELK).
- Experience with LLMs, embeddings, vector databases, prompt engineering, and finetuning workflows.
- Familiarity with Red Hat OpenShift AI initiatives or community projects related to enterprise AI.
- Background in performance profiling, quantization, or model compression for edge/onprem inference.

Regards

Puneet

📌 AIML - Navi Mumbai
🏢 Mount Talent Consulting
📍 Mumbai