Padmi

Senior AI Platform Engineer

IndiaPosted 2 months ago
Software engineeringSeniorFull Time; Regular
Apply at TALENTVIDAS STAFFING SOLUTIONS PRIVATE LIMITED

Opens the source posting on shine.com

Source description

About the role

View original

Job Description :- 4- 6+ years of professional software engineering experience, with at least 3+ years in applied AI / LLM systems.- Experience working in consulting, platform engineering, or accelerator-style reusable asset development.- Prior involvement in data-migration, modernization, or analytics engineering programs is a strong plus.- Strong expertise in LLM-based application development (frameworks such as LangChain, LangGraph, Semantic Kernel, custom orchestration).- Proven experience with agentic design patterns, including :1. Multi-step task planning & decomposition2. Tool-calling / API-driven agents3. Workflow graphs & supervisory agents4. Long-running task coordination- Deep familiarity with context & retrieval design, including :1. RAG pipelines and embedding strategies2. Retrieval quality evaluation3. Grounding and prompt-context isolation4. Vector stores & document indexing- Strong software engineering fundamentals :1. Python (primary) testing, packaging, dependency management2. Architectural design & code quality best-practices3. CI/CD and deployment patterns- Experience designing observability and evaluation loops for AI workflows (telemetry, metrics, regression testing, drift tracking).- Experience integrating LLM systems with :1. Data platforms / warehouses2. Metadata systems and workflow tools3. REST / Microservices architectures- Act as a technical leader and architectural partner across accelerator initiatives.- Coach junior engineers through pairing, reviews, and design walkthroughs.- Advocate for reusable patterns and forward-compatible designs.- Contribute to a culture of experimentation, evidence-based iteration, and shared learning. (ref:hirist.tech) Job Description :- 4- 6+ years of professional software engineering experience, with at least 3+ years in applied AI / LLM systems.- Experience working in consulting, platform engineering, or accelerator-style reusable asset development.- Prior involvement in data-migration, modernization, or analytics engineering programs is a strong plus.- Strong expertise in LLM-based application development (frameworks such as LangChain, LangGraph, Semantic Kernel, custom orchestration).- Proven experience with agentic design patterns, including :1. Multi-step task planning & decomposition2. Tool-calling / API-driven agents3. Workflow graphs & supervisory agents4. Long-running task coordination- Deep familiarity with context & retrieval design, including :1. RAG pipelines and embedding strategies2. Retrieval quality evaluation3. Grounding and prompt-context isolation4. Vector stores & document indexing- Strong software engineering fundamentals :1. Python (primary) testing, packaging, dependency management2. Architectural design & code quality best-practices3. CI/CD and deployment patterns- Experience designing observability and evaluation loops for AI workflows (telemetry, metrics, regression testing, drift tracking).- Experience integrating LLM systems with :1. Data platforms / warehouses2. Metadata systems and workflow tools3. REST / Microservices architectures- Act as a technical leader and architectural partner across accelerator initiatives.- Coach junior engineers through pairing, reviews, and design walkthroughs.- Advocate for reusable patterns and forward-compatible designs.- Contribute to a culture of experimentation, evidence-based iteration, and shared learning. (ref:hirist.tech)

One address, no account. We’ll tell you when matching roles go live.