Senior Software Engineer

JLL empowers you to shape a brighter way . Our people at JLL are shaping the future of real estate for a better world by combining world class services, advisory and technology for our clients. We are committed to hiring the best, most talented people and empowering them to thrive, grow meaningful careers and to find a place where they belong. Whether you’ve got deep experience in commercial real estate, skilled trades or technology, or you’re looking to apply your relevant experience to a new industry, join our team as we help shape a brighter way forward. Senior Software Engineer - AI Engineering Bengaluru Role Summary Embeds with client teams, understands manual business workflows, and builds AI-agent-powered automation to replace them. Helps build a new agent harness platform from the ground up — to be built on Claude (Claude Code / Cowork), AWS Step Functions (ASL) and Amazon Bedrock AgentCore, with an AG-UI front end — and then delivers production workflows on it. Owns the solution end-to-end — discovery, build, deploy, evaluate, iterate — working directly with enterprise customers with minimal direction. TECHNICAL REQUIREMENTS Harness Engineering — Core • Harness engineering — Excellent understanding of designing agent harnesses: the control loop, tool and skill surface, context and state management, and human-in-the-loop checkpoints around an LLM • AWS Step Functions with ASL — Author Amazon States Language state machines to orchestrate agent steps, branching, retries, parallelism and human-approval gates (e.g. task-token waits); invoke AgentCore runtimes and Lambda from workflows • Deterministic vs LLM control — Design workflows where policy gates and rules decide routing and the LLM only proposes, with explicit exception, timeout and loop-guard paths • Amazon Bedrock AgentCore — Host, operate and scale agent workloads on AgentCore Runtime; understand lifecycle, scaling and invocation patterns, and expose tools via AgentCore Gateway • AgentCore Observability — Hands-on tracing, metrics and logging of agent runs (AgentCore, CloudWatch, Datadog) with a per-step audit trail to debug and monitor production workflows • AgentCore Evaluation — Hands-on design and running of evaluations (AgentCore Evaluations, golden-dataset regression tests) to measure agent quality before and after each release • Guardrails — Hands-on configuration of Amazon Bedrock Guardrails and policy controls for safety, prompt-injection defence, PII and hallucination mitigation, with human-in-the-loop review where required Agentic AI with Claude • Claude Code / Cowork — Experience designing, deploying and scaling AI-powered production workflows using Claude Code and/or Cowork • LLM API fundamentals — Tool use, function calling, streaming and context management • Skill building — Design and publish reusable skills consumable by agent workflows • MCP (Model Context Protocol) — Build, host and consume MCP servers (e.g. FastMCP on AgentCore); expose and integrate tools for agent use, with agents reaching data only through MCP/API, never directly • Multi-agent coordination — Task delegation and result aggregation across agents (A2A) • RAG pipelines — Vector databases, chunking, embeddings and retrieval • Prompt engineering — System prompts, evaluation and iteration Front End • AG-UI — Build agent-facing user interfaces on the AG-UI protocol, connecting the front end to running agents for streaming responses, tool-call visibility, shared state and human approval steps Backend • Python 3.10+ — async/await, type hints • FastAPI or equivalent Python web framework • Basic SQL — query, filter, join; awareness of vector DBs (pgvector, Pinecone, OpenSearch) • NoSQL — Working knowledge of document/key-value stores (e.g. Amazon DynamoDB): data modelling, access patterns, and using them for agent run state and audit trails • REST API design, JWT / OAuth2 Workflow Automation • Decompose manual business processes into agent workflows • Document processing — PDF, Excel, unstructured data extraction and classification AI Engineer October 2026 JLL Confidential • OCR — Extract text, tables and layout from scanned and image-based documents (e.g. AWS Textract), and feed the output into agent workflows • Enterprise system integration — SharePoint, email, and external systems via APIs and MCP Infrastructure • AWS services — Lambda, ECS, RDS, S3, IAM — support agent deployment and data storage needs • Terraform / Infrastructure as Code — Provision and promote AgentCore, Step Functions, Lambda and supporting AWS resources across environments • Docker and containerisation • GitHub Actions CI/CD ADDITIONAL SKILLS • Kubernetes • TypeScript • Fine-tuning and model evaluation • CRE domain knowledge EXPERIENCE • Proven experience in software engineering, with hands-on AI engineering shipped to production (years of experience are not the criterion; depth of AI delivery is) • At least one production project involving LLM agents, skill building, or RAG pipelines — ideally on AWS Bedrock AgentCore and/or Step Functions • Direct experience working with enterprise customers to design, deploy and scale AI-powered production workflows using Claude Code / Cowork • Track record of owning and delivering solutions end-to-end with minimal guidance • Experience working directly with non-technical stakeholders — gathering requirements, presenting solutions • Consulting or client-facing background is an advantage Location: On-site –Bengaluru, KA Scheduled Weekly Hours: 40 If this job description resonates with you, we encourage you to apply even if you don’t meet all of the requirements. We’re interested in getting to know you and what you bring to the table! At JLL, we harness the power of artificial intelligence (AI) to efficiently accelerate meaningful connections between candidates and opportunities. Using AI capabilities, we analyze your application for relevant skills, experiences, and qualifications to generate valuable insights about how your unique profile aligns with the specific requirements of the role you're pursuing. JLL Privacy Notice Jones Lang LaSalle (JLL), together with its subsidiaries and affiliates, is a leading global provider of real estate and investment management services. We take our responsibility to protect the personal information provided to us seriously. Generally the personal information we collect from you are for the purposes of processing in connection with JLL’s recruitment process. We endeavour to keep your personal information secure with appropriate level of security and keep for as long as we need it for legitimate business or legal reasons. We will then delete it safely and securely. For more information about how JLL processes your personal data, please view our Candidate Privacy Statement . For additional details please see our career site pages for each country. Jones Lang LaSalle (“JLL”) is an Equal Opportunity Employer and is committed to working with and providing reasonable accommodations to individuals with disabilities. If you need a reasonable accommodation because of a disability for any part of the employment process – including the online application and/or overall selection process – you may email us at [email protected] . This email is only to request an accommodation. Please direct any other general recruiting inquiries to our Contact Us page > I want to work for JLL.